Human pose tracking by parametric annealing

Model based methods to marker-free motion capture have a very high computational overhead. In this paper we describe a method that improves on existing global optimization techniques to tracking articulated objects. Our method improves on the state-of-the-art Annealed Particle Filter (APF) by reusin...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaliamoorthi, Prabhu., Kakarala, Ramakrishna.
Other Authors: School of Computer Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/84313
http://hdl.handle.net/10220/16352
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-84313
record_format dspace
spelling sg-ntu-dr.10356-843132020-05-28T07:17:54Z Human pose tracking by parametric annealing Kaliamoorthi, Prabhu. Kakarala, Ramakrishna. School of Computer Engineering IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2012 : Providence, Rhode Island, US) DRNTU::Engineering::Computer science and engineering Model based methods to marker-free motion capture have a very high computational overhead. In this paper we describe a method that improves on existing global optimization techniques to tracking articulated objects. Our method improves on the state-of-the-art Annealed Particle Filter (APF) by reusing samples across annealing layers and by using an adaptive parametric density for diffusion. We compare the proposed method with APF on a scalable problem and study the effects of dimensionality, multi-modality and the range of search. We perform sensitivity analysis on the parameters of our algorithm and show that it is widely tolerant. We also show results on tracking human pose from the widely-used Human Eva I dataset. Our results show that the proposed method reduces the tracking error despite using less than 50% of the computational resources as APF. The tracked output also shows a significant qualitative improvement over APF. 2013-10-10T03:27:36Z 2019-12-06T15:42:34Z 2013-10-10T03:27:36Z 2019-12-06T15:42:34Z 2012 2012 Conference Paper Kaliamoorthi, P., & Kakarala, R. (2012). Human pose tracking by parametric annealing. 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.36-41. https://hdl.handle.net/10356/84313 http://hdl.handle.net/10220/16352 10.1109/CVPRW.2012.6239235 en
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Kaliamoorthi, Prabhu.
Kakarala, Ramakrishna.
Human pose tracking by parametric annealing
description Model based methods to marker-free motion capture have a very high computational overhead. In this paper we describe a method that improves on existing global optimization techniques to tracking articulated objects. Our method improves on the state-of-the-art Annealed Particle Filter (APF) by reusing samples across annealing layers and by using an adaptive parametric density for diffusion. We compare the proposed method with APF on a scalable problem and study the effects of dimensionality, multi-modality and the range of search. We perform sensitivity analysis on the parameters of our algorithm and show that it is widely tolerant. We also show results on tracking human pose from the widely-used Human Eva I dataset. Our results show that the proposed method reduces the tracking error despite using less than 50% of the computational resources as APF. The tracked output also shows a significant qualitative improvement over APF.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Kaliamoorthi, Prabhu.
Kakarala, Ramakrishna.
format Conference or Workshop Item
author Kaliamoorthi, Prabhu.
Kakarala, Ramakrishna.
author_sort Kaliamoorthi, Prabhu.
title Human pose tracking by parametric annealing
title_short Human pose tracking by parametric annealing
title_full Human pose tracking by parametric annealing
title_fullStr Human pose tracking by parametric annealing
title_full_unstemmed Human pose tracking by parametric annealing
title_sort human pose tracking by parametric annealing
publishDate 2013
url https://hdl.handle.net/10356/84313
http://hdl.handle.net/10220/16352
_version_ 1681057719373529088